© 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. 145311
    Prev
    Next
    INDEX
    Explanations

    claim or blockchain transaction

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

    knowledge and information

    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
    good
    0.47
    tion
    0.44
    asion
    0.43
     nele
    0.43
    ন্তা
    0.43
    丹
    0.42
    のと
    0.41
    のエ
    0.41
    क्के
    0.41
    <unused41>
    0.41
    POSITIVE LOGITS
     Blockchain
    0.52
    Blockchain
    0.48
     blockchain
    0.48
     Predictive
    0.46
    ي
    0.45
    Claim
    0.45
     बिहारी
    0.44
     Geschmack
    0.42
    blockchain
    0.42
    Exclude
    0.42
    Activations Density 0.000%

    No Known Activations