© 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. 154461
    Prev
    Next
    INDEX
    Explanations

    heat radiating

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

    phrases including "with" and parentheticals

    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
     αυτά
    0.47
    weight
    0.43
    ધ્ય
    0.43
     дву
    0.43
    を持つ
    0.43
    Wrapping
    0.42
     악
    0.42
    钢
    0.42
    팽
    0.42
     হাতি
    0.41
    POSITIVE LOGITS
    Antaeotricha
    0.50
     acha
    0.49
    otherapie
    0.46
     importe
    0.45
    വന്‍
    0.44
     பணி
    0.42
     सदन
    0.42
    oko
    0.42
     impor
    0.41
    ilization
    0.41
    Activations Density 0.002%

    No Known Activations