© 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. 156636
    Prev
    Next
    INDEX
    Explanations

    Solo literature

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

    clinical or personal matters

    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
    嘣
    0.46
     चिह्नित
    0.44
     tengah
    0.43
     तिथि
    0.42
    嘁
    0.41
     situate
    0.41
     BlueprintName
    0.40
     menonton
    0.40
     जमाने
    0.40
    घाडी
    0.40
    POSITIVE LOGITS
     Borel
    0.54
    invalid
    0.51
    introduced
    0.48
     divisors
    0.45
    Invalid
    0.44
    omat
    0.44
    introducing
    0.44
     Doris
    0.42
     $
    0.42
    nl
    0.42
    Activations Density 0.000%

    No Known Activations