© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41309
    Prev
    Next
    INDEX
    Explanations

    timing and saving actions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects prepositional constructions indicating being at a particular place at a particular time (as in the idiomatic “in the right/wrong place at the right/wrong time”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     since
    -1.49
    seille
    -1.32
     背影
    -1.24
    nhi
    -1.23
     jeugd
    -1.22
     stále
    -1.20
    posits
    -1.16
     list
    -1.15
     露
    -1.15
    好評
    -1.14
    POSITIVE LOGITS
    떄
    1.34
     grosso
    1.33
    `);
    1.30
    ');
    1.28
     nei
    1.23
     him
    1.22
     outro
    1.20
    ></
    1.20
     negli
    1.20
    </h6>
    1.19
    Activations Density 0.023%

    No Known Activations