© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224992
    Prev
    Next
    INDEX
    Explanations

    insecure attachment, deeply offensive, cheese

    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
    UEN
    0.42
    OfInterest
    0.40
    ABILITY
    0.40
    ariously
    0.40
    ieren
    0.39
    ёнок
    0.38
    юнча
    0.36
     又
    0.36
     യുവ
    0.36
    逦
    0.36
    POSITIVE LOGITS
     NVIDIA
    0.47
     Nvidia
    0.43
     downtime
    0.42
    櫒
    0.40
    ပ်
    0.40
     diode
    0.39
    Psalm
    0.39
     alarma
    0.39
     combination
    0.39
     Goku
    0.39
    Activations Density 0.000%

    No Known Activations