© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19893
    Prev
    Next
    INDEX
    Explanations

    interrogation and confession

    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
     вокруг
    0.43
    Boundary
    0.40
    imethyl
    0.38
    HIP
    0.37
     bridesmaids
    0.37
    attack
    0.37
    Outlet
    0.37
    ॲ
    0.37
    攻击
    0.37
    amanho
    0.36
    POSITIVE LOGITS
     interrogation
    0.92
     interrog
    0.84
     interrogated
    0.82
     confess
    0.81
     interrogate
    0.77
     confession
    0.73
     confes
    0.73
     पूछताछ
    0.69
     confessed
    0.69
     জিজ্ঞাসাবাদ
    0.69
    Activations Density 0.034%

    No Known Activations