© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217088
    Prev
    Next
    INDEX
    Explanations

    health, management, minute, multiple

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

    understanding repetitive melodic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    図
    0.51
    臥
    0.49
    優
    0.48
    confirmed
    0.46
    糞
    0.46
    選
    0.45
    頬
    0.45
    ?...
    0.45
    :...
    0.44
    ลับ
    0.44
    POSITIVE LOGITS
    ListenAnd
    0.46
    ROIT
    0.44
     splike
    0.44
    RefManager
    0.43
     arrhyth
    0.43
    IsMethod
    0.42
    ClF
    0.42
     sikap
    0.41
    زام
    0.40
     erwäh
    0.40
    Activations Density 0.001%

    No Known Activations