© 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. 28945
    Prev
    Next
    INDEX
    Explanations

    prior to

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

    besides or in addition to

    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
    ٻ
    0.40
     ks
    0.40
     llrp
    0.40
     uk
    0.39
     št
    0.39
    ｕ
    0.39
     lh
    0.38
     Boż
    0.38
     lexical
    0.38
     glic
    0.37
    POSITIVE LOGITS
    enburg
    0.40
    <unused63>
    0.39
    acles
    0.38
    inger
    0.37
    parte
    0.37
    </code>
    0.37
    inson
    0.36
    esse
    0.36
    <eos>
    0.36
    rito
    0.35
    Activations Density 0.059%

    No Known Activations