© 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. 100267
    Prev
    Next
    INDEX
    Explanations

    invoice cost or unvested

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

    descriptive adjectives and common words

    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
    я
    0.55
    த்தா
    0.52
    бить
    0.50
    ля
    0.50
    л
    0.49
    нев
    0.48
     налази
    0.48
    го
    0.46
    ందం
    0.46
    色が
    0.46
    POSITIVE LOGITS
     nécessaire
    0.49
     O
    0.46
     tiennent
    0.46
    Query
    0.44
     প্রার্থী
    0.41
     Cf
    0.41
    Dispatch
    0.41
     necesitamos
    0.40
     "")
    0.40
    .")
    0.40
    Activations Density 0.000%

    No Known Activations