© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62850
    Prev
    Next
    INDEX
    Explanations

    love bombing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_l0_small_affine
    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
    茆
    0.38
    ipay
    0.38
     مای
    0.37
    ucristo
    0.37
    createNew
    0.35
     Dealer
    0.35
    ロジー
    0.35
     Shore
    0.34
    ර
    0.34
    रण
    0.34
    POSITIVE LOGITS
     bomb
    2.36
     bombing
    2.30
     bombs
    2.25
     бом
    2.25
    bomb
    2.13
     Bomb
    2.11
    Bomb
    2.09
     bombings
    1.99
     Bom
    1.98
    bom
    1.98
    Activations Density 0.005%

    No Known Activations