© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30648
    Prev
    Next
    INDEX
    Explanations

    "my therapist told me to"

    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_65k_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
    ሉ።
    0.46
    および
    0.43
    ופ
    0.42
     cunt
    0.42
    &&(
    0.41
    юр
    0.41
    ógicos
    0.41
    émico
    0.41
     berkel
    0.40
    qualiter
    0.40
    POSITIVE LOGITS
     ఈ
    0.46
    Princess
    0.44
     ello
    0.43
     This
    0.42
     Engagement
    0.41
     നാല
    0.40
     However
    0.40
     Analyst
    0.40
     Magnum
    0.40
     Two
    0.40
    Activations Density 0.007%

    No Known Activations