© 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. 193737
    Prev
    Next
    INDEX
    Explanations

    specific clauses or rules

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

    robotics advances and human interaction

    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
    Orig
    0.53
     ય
    0.49
     indic
    0.46
     Orig
    0.46
     здоров
    0.46
     подобные
    0.46
     solito
    0.45
     varia
    0.45
     errori
    0.45
     способны
    0.44
    POSITIVE LOGITS
    u
    0.53
    \\
    0.53
    er
    0.49
    Γ
    0.46
     pancreatitis
    0.45
    ும்
    0.44
     Dementia
    0.44
     Siemens
    0.44
    /
    0.44
    ⤒
    0.44
    Activations Density 0.000%

    No Known Activations