© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135163
    Prev
    Next
    INDEX
    Explanations

    specify requirements

    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_40_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
     Escal
    0.46
     escal
    0.45
     escalate
    0.45
    ⠀⠀
    0.42
     escalated
    0.42
     escalation
    0.42
    ESC
    0.42
     dalle
    0.42
    ட்டை
    0.41
    સ્થા
    0.40
    POSITIVE LOGITS
     hyp
    0.40
    amaran
    0.40
     types
    0.38
    autos
    0.38
    hom
    0.37
     homophobic
    0.37
    kinds
    0.37
    缅
    0.37
     freeing
    0.37
    examples
    0.36
    Activations Density 0.001%

    No Known Activations