© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37802
    Prev
    Next
    INDEX
    Explanations

    explicit sexual details

    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_31_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
    ✍
    0.43
    缺点
    0.42
     कॉलोनी
    0.41
    奻
    0.40
     अच्छा
    0.40
    Software
    0.39
    ctus
    0.39
    ByDefault
    0.38
    <unused417>
    0.38
    న్
    0.37
    POSITIVE LOGITS
     parameters
    0.55
     posits
    0.53
     comorbidities
    0.52
     epistem
    0.51
     proposed
    0.51
     investigadores
    0.49
     epigenetic
    0.47
     opioids
    0.46
     epigen
    0.46
     fantasies
    0.46
    Activations Density 0.003%

    No Known Activations