© 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. 220798
    Prev
    Next
    INDEX
    Explanations

    Investigating and investigative tasks

    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
    <0x9F>
    0.48
    盆
    0.48
    ні
    0.45
    ţi
    0.44
    <0x9C>
    0.44
    anya
    0.43
    <0x99>
    0.42
    nement
    0.42
    ⟶
    0.42
    şi
    0.41
    POSITIVE LOGITS
    स
    0.51
    ک
    0.51
     следова
    0.47
     envo
    0.47
     affix
    0.46
    ア
    0.46
     felonies
    0.46
     соединения
    0.45
    HQ
    0.44
     subpoenas
    0.44
    Activations Density 0.007%

    No Known Activations