© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30812
    Prev
    Next
    INDEX
    Explanations

    decimal point or Google immediately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cobrar
    0.43
     seves
    0.42
    อะไร
    0.42
     সরকার
    0.41
     равен
    0.40
     civic
    0.40
     coercion
    0.40
     為
    0.40
     ductility
    0.40
     polymerase
    0.39
    POSITIVE LOGITS
    เคร
    0.46
     Profes
    0.40
     Nghi
    0.39
    彷
    0.39
    roh
    0.39
     Invest
    0.39
     Sle
    0.38
     Speakers
    0.38
     flound
    0.38
     Ramb
    0.38
    Activations Density 0.000%

    No Known Activations