© 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. 99623
    Prev
    Next
    INDEX
    Explanations

    conjunctions or pronouns followed by nouns/verbs

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

    uses permission, host, background, action

    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
    <unused51>
    0.49
    transitions
    0.47
     altitude
    0.45
    াদন
    0.44
     কোনটি
    0.44
    海拔
    0.44
    复杂度
    0.43
    留在
    0.43
    如何
    0.42
    ষ্টার
    0.42
    POSITIVE LOGITS
    t
    0.45
    ted
    0.42
    f
    0.42
    latest
    0.42
    infos
    0.40
    '
    0.40
    podcast
    0.39
    free
    0.38
    acak
    0.38
    d
    0.38
    Activations Density 0.000%

    No Known Activations