© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169771
    Prev
    Next
    INDEX
    Explanations

    emotional support

    np_acts-logits-general · gemini-2.5-flash-lite

    bushes ahead, dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    צות
    0.52
     WHAT
    0.49
    에서의
    0.48
     гуляць
    0.46
    ДЕ
    0.46
     CCSDT
    0.46
    𝙖
    0.46
    CORDS
    0.46
    Це
    0.46
    стре
    0.46
    POSITIVE LOGITS
    োধ
    0.51
     bathroom
    0.44
     diar
    0.43
     marked
    0.42
    ادار
    0.41
     mark
    0.40
    股
    0.40
    ুরি
    0.40
    ന്നെ
    0.40
    instrList
    0.40
    Activations Density 0.000%

    No Known Activations