© 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. 49211
    Prev
    Next
    INDEX
    Explanations

    verbs followed by punctuation

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

    Status, cloning, intent, burns, skills

    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
     {}\
    0.43
    don
    0.42
    ificaciones
    0.41
    dfe
    0.41
    पीएफ
    0.41
     Often
    0.40
    dist
    0.40
    일
    0.40
    럴
    0.40
     لات
    0.39
    POSITIVE LOGITS
    вшая
    0.56
     правил
    0.55
     нашей
    0.49
     dakkh
    0.49
     graça
    0.48
    ло
    0.46
     vacanam
    0.46
    IVERS
    0.46
     τόσο
    0.46
    ATIV
    0.46
    Activations Density 0.000%

    No Known Activations