© 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. 61153
    Prev
    Next
    INDEX
    Explanations

    resolving issues, reflections, post comments

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

    fuzz testing, assessment, poem jokes

    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
     IST
    0.48
     Ö
    0.46
     Provider
    0.42
     ღ
    0.42
     Sebast
    0.41
     NLP
    0.41
     Sp
    0.41
    塹
    0.40
     Stealth
    0.40
     SCT
    0.40
    POSITIVE LOGITS
     डांस
    0.50
     بواسطة
    0.49
    usakan
    0.45
     ciem
    0.45
     μέσω
    0.44
     करिए
    0.42
     udara
    0.41
     delicioso
    0.41
     bagno
    0.40
    adf
    0.40
    Activations Density 0.000%

    No Known Activations