© 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. 43363
    Prev
    Next
    INDEX
    Explanations

    not ocean city or mountain city

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

    characters, journey, finding, feel

    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
    cando
    0.53
    mild
    0.46
    quito
    0.46
     Equatorial
    0.45
    o
    0.45
    oeste
    0.45
     Pets
    0.44
     огне
    0.44
    phalt
    0.44
    cylinder
    0.44
    POSITIVE LOGITS
    価値
    0.46
    امی
    0.43
    残念
    0.42
    اع
    0.42
     ارزش
    0.41
    Software
    0.40
    GetResponse
    0.40
    詐
    0.40
    案件
    0.40
     empiezan
    0.39
    Activations Density 0.001%

    No Known Activations