© 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. 69538
    Prev
    Next
    INDEX
    Explanations

    no, savings, chance, thousand

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

    landslides and melting

    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
    rotl
    0.49
    amburger
    0.47
    igare
    0.42
    liang
    0.41
    আ
    0.41
     enlighten
    0.40
     zanim
    0.40
    hanti
    0.40
    étaires
    0.39
    getOrder
    0.39
    POSITIVE LOGITS
    ス
    0.52
     basée
    0.48
    с
    0.46
     inactivació
    0.45
     sabot
    0.45
    годня
    0.44
    に基づ
    0.44
     ransomware
    0.44
    イン
    0.43
     massif
    0.43
    Activations Density 0.000%

    No Known Activations