© 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. 87615
    Prev
    Next
    INDEX
    Explanations

    Controvers, onsite, list

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

    but expensive

    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
    📈
    0.51
    થ
    0.50
    deterministic
    0.47
    нам
    0.47
    😌
    0.46
    healthcare
    0.46
    昏
    0.45
    dating
    0.45
    commutative
    0.45
    ⺆
    0.45
    POSITIVE LOGITS
     lens
    0.47
    </strong>
    0.47
     Ariel
    0.46
     decoy
    0.45
     a
    0.45
    ivities
    0.44
     lenses
    0.43
     both
    0.43
     licenses
    0.43
     infring
    0.42
    Activations Density 0.000%

    No Known Activations