© 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-65K
    7. 52195
    Prev
    Next
    INDEX
    Explanations

    Bharat Ganarajya

    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_65k_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
    すごく
    0.50
    或者是
    0.46
    携
    0.43
    نسب
    0.43
    /
    0.43
    ፍተኛ
    0.42
    あるいは
    0.42
     as
    0.41
    α
    0.40
    很有
    0.40
    POSITIVE LOGITS
     ansiedad
    0.45
    Species
    0.45
    Fuck
    0.45
    Wan
    0.44
    亞洲
    0.44
    <unused67>
    0.44
     cidades
    0.44
     población
    0.43
     construcción
    0.43
     riot
    0.42
    Activations Density 0.009%

    No Known Activations