© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9898
    Prev
    Next
    INDEX
    Explanations

    goals

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

    The neuron fires strongly on words referring to goals or objectives (e.g. “goal,” “goals,” “objectives”).

    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
     Diese
    -2.69
    sonaro
    -2.58
     этом
    -2.53
    vantaged
    -2.48
     overt
    -2.44
    谖
    -2.39
    }
    -2.34
     hermosas
    -2.33
     großen
    -2.31
     amikor
    -2.31
    POSITIVE LOGITS
    </strong>
    3.02
    ra
    2.58
     eletrônico
    2.50
    li
    2.47
    LY
    2.44
    le
    2.39
     anello
    2.36
    ti
    2.34
    是很
    2.34
    '
    2.33
    Activations Density 0.015%

    No Known Activations