© 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. 44068
    Prev
    Next
    INDEX
    Explanations

    links are or around

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

    regulation, inclusion, facts, CTR, ideas

    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
    ম
    0.41
    ]>
    0.40
    imperial
    0.39
     ihnen
    0.38
     миллиар
    0.38
    DISTANCE
    0.37
    ᱑
    0.37
    ৬
    0.37
    Hotel
    0.37
     MULT
    0.37
    POSITIVE LOGITS
     références
    0.45
     playerName
    0.43
     aku
    0.42
     tõ
    0.42
     dolayı
    0.41
     apoy
    0.40
     eva
    0.40
     acqua
    0.39
     liens
    0.38
     erlaubt
    0.38
    Activations Density 0.000%

    No Known Activations