© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 24146
    Prev
    Next
    INDEX
    Explanations

    difference and experimental setup

    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
    Ⴖ
    0.45
    AppCompatTheme
    0.41
     órgão
    0.41
    ังหวัด
    0.40
     اظہار
    0.39
    看完
    0.39
    रावट
    0.39
    न्होंने
    0.39
     pripre
    0.39
    alignat
    0.38
    POSITIVE LOGITS
    В
    0.51
    W
    0.48
     consists
    0.47
    BY
    0.45
    C
    0.45
    c
    0.45
    X
    0.44
    Z
    0.43
     means
    0.43
    V
    0.43
    Activations Density 0.000%

    No Known Activations