© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4013
    Prev
    Next
    INDEX
    Explanations

    names followed by last names

    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_31_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
     Siamese
    0.33
     VLAN
    0.31
     Parameter
    0.30
     Lollipop
    0.30
    HOBBIT
    0.30
    ➛
    0.29
    အတွ
    0.29
    CurrentImage
    0.29
    笄
    0.28
    扃
    0.28
    POSITIVE LOGITS
    .
    0.26
     who
    0.24
    ford
    0.24
     says
    0.23
    us
    0.21
     Johnson
    0.21
     explains
    0.20
    а
    0.20
     I
    0.20
    દ
    0.20
    Activations Density 0.046%

    No Known Activations