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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74013
    Prev
    Next
    INDEX
    Explanations

    loading data from files

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     delà
    -1.44
     rése
    -1.38
    lised
    -1.35
    はその
    -1.31
    vább
    -1.27
     menthe
    -1.27
    lI
    -1.26
     "','
    -1.25
     relata
    -1.24
    nament
    -1.23
    POSITIVE LOGITS
     something
    1.67
     because
    1.51
     or
    1.46
    Recently
    1.45
     being
    1.45
     using
    1.41
     [''],
    1.38
     as
    1.34
    ございました
    1.34
     recently
    1.34
    Activations Density 0.072%

    No Known Activations