© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84047
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by linkers

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

    exploitation and abuse

    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
    Not in Any Lists

    No Comments

    Negative Logits
     elektry
    0.47
     பயன்படுகிறது
    0.45
     POSSIBILITY
    0.44
     உதவுக
    0.44
    日本では
    0.44
     ELECTRIC
    0.44
    Khokhlov
    0.44
    ﾞ
    0.44
    還可以
    0.44
    電気
    0.43
    POSITIVE LOGITS
    ٤
    0.45
     Psalms
    0.45
     reviewers
    0.43
     Drs
    0.43
    uncak
    0.40
     ensue
    0.40
     sisters
    0.40
     наших
    0.39
     Sisters
    0.39
    yla
    0.38
    Activations Density 0.000%

    No Known Activations