© 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. 20154
    Prev
    Next
    INDEX
    Explanations

    club showcase

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

    instructions and explanations

    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
    ütü
    0.45
    matik
    0.44
    require
    0.42
    gherita
    0.42
    .
    0.42
    ,.
    0.42
    bei
    0.41
    ורך
    0.41
     вста
    0.41
     হেড
    0.41
    POSITIVE LOGITS
    तह
    0.49
     carro
    0.45
     proofs
    0.45
     förm
    0.45
     axles
    0.45
    Renault
    0.44
     néanmoins
    0.43
     fibr
    0.42
    漁
    0.42
     disgu
    0.42
    Activations Density 0.000%

    No Known Activations