© 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. 149657
    Prev
    Next
    INDEX
    Explanations

    my personal, the fullest

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

    opposite of

    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
     будущем
    0.45
     некоторым
    0.45
     которому
    0.44
    近日
    0.42
    福岡
    0.42
    頓
    0.42
     Zweiten
    0.42
     prick
    0.42
     दोन्ही
    0.42
     anci
    0.41
    POSITIVE LOGITS
    isil
    0.50
    niv
    0.48
    arına
    0.45
    /-
    0.45
    coma
    0.44
     arrives
    0.44
    aband
    0.44
     চিঠ
    0.44
     tastings
    0.44
    ạc
    0.43
    Activations Density 0.001%

    No Known Activations