© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    word endings and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2148>
    0.88
    ﹐
    0.86
    ovaniyu
    0.85
    ividades
    0.83
    <unused2184>
    0.82
    estes
    0.82
    📠
    0.81
    ård
    0.81
    ínas
    0.81
    <unused2152>
    0.81
    POSITIVE LOGITS
     heuristic
    0.63
     logical
    0.62
     recursive
    0.58
    timestamp
    0.55
     time
    0.54
     finite
    0.54
     theoretical
    0.53
     bootstrapping
    0.52
     confound
    0.52
     godly
    0.51
    Activations Density 0.223%

    No Known Activations