© 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. 70465
    Prev
    Next
    INDEX
    Explanations

    details and information seeking

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

    referring to ports

    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
    槨
    0.46
     খুঁ
    0.45
     advisable
    0.45
    ৃত্বে
    0.45
     muốn
    0.44
     understated
    0.44
    angkap
    0.43
     artisanal
    0.42
     inzwischen
    0.42
     underwhelming
    0.41
    POSITIVE LOGITS
    Learning
    0.47
    ร
    0.43
    OrFail
    0.41
    !
    0.41
    ۔
    0.40
    .;
    0.40
    ю
    0.40
    January
    0.40
    Free
    0.40
     FREE
    0.40
    Activations Density 0.000%

    No Known Activations