© 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. 40-GEMMASCOPE-2-RES-65K
    7. 54780
    Prev
    Next
    INDEX
    Explanations

    a way

    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_40_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
    First
    0.45
     Classical
    0.42
    Classical
    0.42
    摊
    0.41
    ูด
    0.41
     Insight
    0.41
    ставка
    0.40
    ρική
    0.40
    Appointment
    0.40
    Bounded
    0.39
    POSITIVE LOGITS
    AFP
    0.44
     এরূপ
    0.42
    achite
    0.42
     considerare
    0.40
    ~~
    0.38
     AFP
    0.38
     उत्पन्न
    0.38
     necesitan
    0.38
     thicken
    0.38
     quiero
    0.38
    Activations Density 0.007%

    No Known Activations