© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 81
    Prev
    Next
    INDEX
    Explanations

    song structure labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ar
    1.31
    a
    1.30
    ed
    1.19
    es
    1.18
    us
    1.14
    -
    1.13
    ag
    1.11
    en
    1.10
    at
    1.10
    as
    1.09
    POSITIVE LOGITS
    <unused1252>
    1.74
     vattum
    1.70
    <unused1952>
    1.67
     theseKeys
    1.67
    <unused2001>
    1.66
     eğer
    1.62
     यह
    1.61
    这不是
    1.61
    <unused2090>
    1.61
    <unused158>
    1.60
    Activations Density 0.753%

    No Known Activations