© 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. 29888
    Prev
    Next
    INDEX
    Explanations

    relationships between

    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
    machen
    0.53
     perfettamente
    0.48
    де
    0.47
    RIA
    0.47
    མ
    0.46
    Nếu
    0.46
    .\\
    0.45
    ક
    0.45
    ори
    0.44
    ма
    0.44
    POSITIVE LOGITS
    दर्शिता
    0.51
     censor
    0.46
     आमिर
    0.46
     آن
    0.43
    卋
    0.43
     rigor
    0.43
     channeling
    0.43
     aura
    0.42
    ementia
    0.42
     జరిగింది
    0.42
    Activations Density 0.002%

    No Known Activations