© 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. 51195
    Prev
    Next
    INDEX
    Explanations

    qualifying contrasts

    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
    േഷ
    0.46
    ቈ
    0.45
    esz
    0.45
    Σ
    0.44
     sequenced
    0.43
    𝘔
    0.43
    лся
    0.43
    ྗ
    0.42
    Нау
    0.42
     induces
    0.41
    POSITIVE LOGITS
     Alhamdulillah
    0.41
     safeguard
    0.39
     miglior
    0.38
     tranquilidad
    0.38
     terci
    0.38
     raio
    0.38
    ﮅ
    0.37
     migliori
    0.37
     मजबूती
    0.37
     betterment
    0.37
    Activations Density 0.030%

    No Known Activations