© 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. 112368
    Prev
    Next
    INDEX
    Explanations

    based on

    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
     blankets
    0.45
     alf
    0.43
    l
    0.42
     ба
    0.41
     traps
    0.41
     সার্ভ
    0.40
     לפ
    0.40
     trips
    0.40
     send
    0.39
     ла
    0.39
    POSITIVE LOGITS
    jectories
    0.46
     সৌরভ
    0.43
    monds
    0.42
    PathResource
    0.41
    ições
    0.40
     Recursos
    0.40
     Outcomes
    0.40
    classname
    0.40
    隀
    0.40
    ischem
    0.39
    Activations Density 0.007%

    No Known Activations