© 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-262K
    7. 169591
    Prev
    Next
    INDEX
    Explanations

    Go to

    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_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
     politician
    0.44
    clickHandler
    0.38
     আরম্ভ
    0.37
     lanthan
    0.37
    ᅴ
    0.37
     vorbere
    0.36
    倜
    0.36
     relig
    0.36
     terj
    0.36
    Aluno
    0.36
    POSITIVE LOGITS
    C
    0.44
    화
    0.42
    华
    0.41
    मेद
    0.40
    器
    0.39
     מיי
    0.39
    化
    0.38
     SCORE
    0.37
    ாக்கு
    0.37
    owa
    0.36
    Activations Density 0.000%

    No Known Activations