© 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. 109259
    Prev
    Next
    INDEX
    Explanations

    business size

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

    consequences and attributes

    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
    食べ
    0.48
     unat
    0.46
    美人
    0.46
     második
    0.46
    免疫
    0.45
    磪
    0.45
    彫
    0.45
    
    0.45
     бес
    0.45
    ခြေ
    0.45
    POSITIVE LOGITS
     incumbent
    0.53
     Model
    0.49
    in
    0.49
    Zb
    0.49
     Student
    0.47
     the
    0.47
     Empirical
    0.47
     fabricant
    0.46
     Poly
    0.46
    Model
    0.46
    Activations Density 0.000%

    No Known Activations