© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47349
    Prev
    Next
    INDEX
    Explanations

    requests identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ><
    0.40
     longevity
    0.40
     fascination
    0.40
    ophthal
    0.40
     limp
    0.39
     indulging
    0.39
     meditative
    0.38
     amazement
    0.37
    ượng
    0.37
    loft
    0.37
    POSITIVE LOGITS
     ::=
    0.48
     vuttam
    0.44
     acabar
    0.43
    Stderr
    0.43
     erken
    0.43
     proveedor
    0.43
    طبيق
    0.42
     kami
    0.42
    ួ
    0.42
     searchValue
    0.41
    Activations Density 0.001%

    No Known Activations