© 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. 1756
    Prev
    Next
    INDEX
    Explanations

    things going wrong at bad times

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

    unintended negative consequences

    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
     +:+
    0.45
    .??.??"]
    0.43
    Reduced
    0.42
    ⼦
    0.41
     való
    0.40
     appreci
    0.40
     சுவா
    0.40
    textepsilon
    0.40
    も見
    0.40
     authentically
    0.39
    POSITIVE LOGITS
     annoying
    0.99
     frustrating
    0.87
    😩
    0.86
    😫
    0.84
     stupid
    0.82
     crappy
    0.82
     irritating
    0.80
     intermin
    0.79
     annoy
    0.79
     stupidity
    0.79
    Activations Density 0.190%

    No Known Activations