© 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. 55367
    Prev
    Next
    INDEX
    Explanations

    before "but" or "after"

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

    building a fictional attacker

    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
    睃
    0.43
     diminish
    0.42
    にします
    0.41
    收
    0.40
     change
    0.40
    ابة
    0.39
     devoid
    0.39
     discernible
    0.39
     edged
    0.38
    逑
    0.38
    POSITIVE LOGITS
    DONE
    0.49
    when
    0.45
    🏇
    0.45
    ในช่วง
    0.44
    WHEN
    0.44
    phill
    0.44
    nights
    0.44
     তাৎ
    0.43
     ช่วง
    0.43
    ⌈
    0.43
    Activations Density 0.000%

    No Known Activations