© 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. 54422
    Prev
    Next
    INDEX
    Explanations

    proper nouns and common abbreviations

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

    EQ Matching

    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
    chied
    0.48
    汅
    0.47
     malzeme
    0.45
     rl
    0.45
     reactants
    0.43
    बई
    0.42
    یث
    0.42
     reactant
    0.42
     Indices
    0.42
    唦
    0.42
    POSITIVE LOGITS
    姓
    0.50
    atm
    0.47
    pessoa
    0.41
    投げ
    0.40
    atis
    0.40
    borough
    0.39
    atus
    0.39
    ptions
    0.38
    erton
    0.38
    person
    0.38
    Activations Density 0.000%

    No Known Activations