© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48910
    Prev
    Next
    INDEX
    Explanations

    `ng` commands

    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_40_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
     namam
    0.41
     Président
    0.37
     kullanılır
    0.37
     کھیلیں
    0.37
    setInput
    0.37
     fournis
    0.36
    밈
    0.36
     prochains
    0.36
    碁
    0.36
     Sacrament
    0.35
    POSITIVE LOGITS
     addressing
    0.39
    ቲ
    0.39
    ศาส
    0.36
    dropping
    0.36
    もあった
    0.35
    Addressing
    0.35
     नील
    0.35
    𝟐
    0.35
    aving
    0.34
     Jalis
    0.34
    Activations Density 0.002%

    No Known Activations