© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130587
    Prev
    Next
    INDEX
    Explanations

    services and requirements

    np_acts-logits-general · gemini-2.5-flash-lite

    weighted, responsibility, humans, dialogue, consciousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VoIP
    0.49
    𝘋
    0.48
     MY
    0.48
    Д
    0.48
     których
    0.47
     niewiel
    0.47
    MY
    0.46
     FROM
    0.46
     amely
    0.46
     χρησιμοποι
    0.46
    POSITIVE LOGITS
    புரி
    0.50
     ලෙස
    0.43
     بمعنى
    0.43
    addSprite
    0.42
    turquoise
    0.42
    θυν
    0.41
    }):=\
    0.40
    પણ
    0.40
    Func
    0.40
    Georg
    0.40
    Activations Density 0.000%

    No Known Activations