© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153121
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    and
    0.58
    C
    0.57
    P
    0.56
    i
    0.55
    d
    0.55
    -
    0.55
    D
    0.55
    <0xE2>
    0.54
    Tech
    0.54
    R
    0.54
    POSITIVE LOGITS
     tumeurs
    0.51
    URNIZOR
    0.49
    OLYBD
    0.47
    髌
    0.47
     endometri
    0.47
     antidepress
    0.47
    parvec
    0.46
     theseKeys
    0.46
     renversement
    0.46
     triángulos
    0.46
    Activations Density 0.005%

    No Known Activations