© 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. 128111
    Prev
    Next
    INDEX
    Explanations

    less grabbing

    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
     Debido
    0.44
     cost
    0.42
     Roman
    0.42
     GBP
    0.41
     PubMed
    0.41
     EUR
    0.41
     VCS
    0.41
     З
    0.40
     literate
    0.40
     Malt
    0.40
    POSITIVE LOGITS
    این
    0.52
    findings
    0.51
    ość
    0.50
    䀘
    0.50
    ंति
    0.50
    lers
    0.49
    𝙜
    0.47
    <unused2125>
    0.47
    ᵢ
    0.47
    StaffID
    0.47
    Activations Density 0.007%

    No Known Activations