© 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. 231307
    Prev
    Next
    INDEX
    Explanations

    move around

    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
    medi
    0.47
    prend
    0.46
    aved
    0.45
    ركه
    0.45
    ModelComponent
    0.44
    çao
    0.44
    やす
    0.44
    ｒ
    0.44
    ̣i
    0.43
    w
    0.43
    POSITIVE LOGITS
     concerns
    0.56
     delights
    0.55
     demolition
    0.52
     disposable
    0.52
     posits
    0.52
     lecture
    0.51
     تشکیل
    0.51
    ㅇ
    0.51
    ЛЬ
    0.50
     raffle
    0.50
    Activations Density 0.000%

    No Known Activations