© 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. 19162
    Prev
    Next
    INDEX
    Explanations

    specific technical mechanisms

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

    Sales, actions, deposition, verify

    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
    ificance
    0.46
    ირი
    0.44
     चिर
    0.44
    ”
    0.44
    ingredients
    0.44
    ING
    0.42
     PROGRESS
    0.42
                        
    0.42
    _______
    0.41
    _________
    0.41
    POSITIVE LOGITS
     wikipagina
    0.53
     admi
    0.50
     écrite
    0.49
     müş
    0.49
    ytte
    0.47
     Gérard
    0.47
     procédé
    0.47
     děti
    0.47
     문
    0.46
     言っ
    0.46
    Activations Density 0.000%

    No Known Activations