© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11860
    Prev
    Next
    INDEX
    Explanations

    working, type, losing, control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    ũng
    1.16
    ْب
    1.15
    andu
    1.13
     enforcement
    1.12
     Rubber
    1.11
     EDUC
    1.10
     skeptic
    1.10
    о
    1.10
     LSP
    1.09
     blessing
    1.07
    POSITIVE LOGITS
    a
    1.52
     erau
    1.29
    ות
    1.28
    aile
    1.24
     nowe
    1.18
     hampir
    1.18
    在一个
    1.13
    瞿
    1.12
     verdi
    1.12
     formado
    1.11
    Activations Density 0.000%

    No Known Activations