© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5942
    Prev
    Next
    INDEX
    Explanations

    reported speech attributing statements

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

    mycelial networks

    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_53_width_65k_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
     enggak
    0.57
     মাননীয়
    0.47
    𝐾
    0.47
     đc
    0.47
     Presumably
    0.46
     þis
    0.45
    (“
    0.45
     þat
    0.43
     Президента
    0.43
    ․
    0.42
    POSITIVE LOGITS
     AFP
    1.61
    AFP
    1.49
    Agence
    0.52
     jihad
    0.50
     emblematic
    0.49
     αφ
    0.45
    alpha
    0.43
     US
    0.43
     AFD
    0.43
    sha
    0.42
    Activations Density 0.019%

    No Known Activations